Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
skybrian
9 months ago
|
parent
|
context
|
favorite
| on:
Defeating Nondeterminism in LLM Inference
If nothing has changed, caching the result would certainly be cheaper. But if you're doing that as part of a test, it's not really
running
the test and it might defeat the purpose of the test.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: